Transcrit en texte un fichier audio ou video accessible par une URL publique en HTTPS. La langue est detectee automatiquement. Le fichier est plafonne a 25 Mo.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL HTTPS publique du fichier audio ou video. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral disclosure burden. It reveals meaningful operational constraints: public HTTPS access, 25 MB file limit, and automatic language detection. It does not mention response format or error behavior, but the core operation and limitations are transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three short sentences with no filler. The main action is front-loaded, and each subsequent sentence adds a necessary constraint or behavior.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple single-parameter tool with no output schema, the description provides enough context to invoke it correctly: what input to provide, what constraints apply, and what the tool does. It could be slightly stronger by describing the output form more explicitly, but 'en texte' already implies the transcript result.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the single parameter 'url' is already described in the schema as 'URL HTTPS publique du fichier audio ou video.' The description adds useful file-level context such as the 25 MB limit and audio/video support, but it does not add significant parameter-level semantics beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Transcrit en texte'), the resource ('un fichier audio ou video accessible par une URL publique en HTTPS'), and the result (text). It is easily distinguishable from sibling tools like kooma_list_voices, kooma_text_to_speech, and kooma_translate, which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear conditions for use: the input must be a public HTTPS audio/video URL, the language is auto-detected, and the file cannot exceed 25 MB. It does not explicitly contrast with sibling tools or state when not to use it, but the use case is well specified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a clearly distinct operation: voice discovery, speech synthesis, transcription from a URL, and translation. The only related pair, kooma_list_voices and kooma_text_to_speech, is explicitly designed as a dependency rather than an overlap.
All tools share the consistent kooma_ prefix and snake_case convention, with most names using straightforward verbs. kooma_text_to_speech breaks the verb-led pattern slightly, but the overall naming scheme remains predictable and readable.
With four tools, the server is tightly scoped to its core Bambara language tasks: text-to-speech, transcription, and translation. Every tool serves a distinct function and none feels redundant or extraneous.
The set covers the essential operations for each advertised capability, including a voice-list helper before synthesis and transcription from public URLs. Minor gaps such as a language-list helper for translation or local-file transcription are workable but not critical.
